CN117950370A - Information processing apparatus and information processing method - Google Patents

Abstract

The invention provides an information processing apparatus and an information processing method capable of predicting the state of a processing object after processing is performed on the processing object with high precision. The information processing device includes: a generation unit configured to generate simulation data including a plurality of combinations of pre-processing data of the object to be processed and post-processing data of the object to be processed after performing a process on the object to be processed under predetermined processing conditions, the combinations including the pre-processing data and the post-processing data when the process is performed at a plurality of pattern densities for each of a plurality of mask shapes; and a deriving unit configured to derive simulation parameters of the shape simulator based on the proximity of the predicted data predicted by inputting the pre-processing data included in the simulation data to the shape simulator and the post-processing data combined with the pre-processing data.

Description

Information processing apparatus and information processing method

Technical Field

The present invention relates to an information processing apparatus and an information processing method.

Background

A process execution device such as a semiconductor manufacturing device executes a process on an object to be processed under predetermined processing conditions, thereby performing a desired shape processing and surface processing. In order to optimize the processing conditions of the process performed by the process execution means, the post-processing data of the object to be processed is predicted using model data constructed to reproduce the variation of the object to be processed as the effect of the process.

For example, patent document 1 discloses an information processing apparatus that receives input of start state data of a subject and end state data of a subject as targets, predicts the end state data of the subject using model data constructed to reproduce a change of the subject as an effect of a process, and determines a process condition of the process performed on the subject based on a proximity of the predicted end state data of the subject to the end state data of the subject as targets.

Prior art literature

Patent literature

Patent document 1: international publication No. 2019/131608

Disclosure of Invention

Technical problem to be solved by the invention

The present invention provides a technique capable of predicting the state of a processing object after processing is performed on the processing object with high precision.

Technical scheme for solving technical problems

According to one aspect of the present invention, there is provided an information processing apparatus including: a generation unit configured to be capable of generating simulation data including a plurality of combinations of pre-processing data of the object to be processed and post-processing data of the object to be processed after performing a process under predetermined processing conditions, the combinations including the pre-processing data and the post-processing data when the process is performed at a plurality of pattern densities for each of a plurality of mask shapes; and a deriving unit configured to derive simulation parameters of the shape simulator based on the proximity of the predicted data predicted by inputting the pre-processing data included in the simulation data to the shape simulator and the post-processing data combined with the pre-processing data.

Effects of the invention

According to one aspect, the state of the object after the processing is performed on the object can be predicted with high accuracy.

Drawings

FIG. 1 is a block diagram showing an example of a substrate processing system.

Fig. 2 is a block diagram showing an example of a hardware configuration of a computer.

Fig. 3 is a conceptual diagram illustrating an example of collected data.

Fig. 4 is a block diagram showing an example of a functional configuration of the parameter deriving device.

Fig. 5 is a block diagram showing a specific example of the processing of the generating unit.

Fig. 6 is a conceptual diagram showing a specific example of the simulation data.

Fig. 7 is a conceptual diagram showing a specific example of the simulation data.

Fig. 8 is a conceptual diagram showing a specific example of the simulation data.

Fig. 9 is a block diagram showing a specific example of processing at the headquarter.

Fig. 10 is a diagram showing a specific example of the recipe parameters.

Fig. 11 is a diagram showing a specific example of the simulation parameters.

Fig. 12 is a block diagram showing a specific example of the processing of the calculating unit.

Fig. 13 is a block diagram showing a specific example of the processing of the deriving unit.

Fig. 14 is a flowchart showing an example of a parameter derivation method.

Fig. 15 is a block diagram showing an example of the functional configuration of the processing condition optimizing apparatus.

Fig. 16 is a specific example of model data.

Fig. 17 is a conceptual diagram showing a specific example of modulated image data.

Fig. 18 is a conceptual diagram showing a specific example of modulated image data.

Fig. 19 is a flowchart showing an example of a process condition optimization method.

Fig. 20 is a conceptual diagram showing an example of a process of reading a combination of a plurality of model data.

Fig. 21 is a conceptual diagram illustrating an example of a process of reading a combination of a plurality of model data.

Fig. 22 is a conceptual diagram showing an example of a process of reading a combination of a plurality of model data.

Fig. 23 is a conceptual diagram illustrating an example of the prediction process.

Fig. 24 is a conceptual diagram showing an example of the processing condition optimizing apparatus.

Fig. 25 is a conceptual diagram illustrating an example of the processing condition optimizing apparatus.

Description of the reference numerals

1. Substrate processing system

10. Substrate processing apparatus

101. Set value input unit

102. Condition input unit

103. Process control unit

11. Measuring device

12. Parameter deriving device

121. Parameter deriving unit

122. Collected data storage unit

123. Analog data storage unit

13. Shape simulator

14. Processing condition optimizing device

140. Model storage unit

141. Data input unit

142. Modulation unit

143. Prediction unit

144. Determination unit

145. And a set value output unit.

Detailed Description

Hereinafter, modes for carrying out the present invention will be described with reference to the drawings. In the drawings, the same components are denoted by the same reference numerals, and overlapping description may be omitted.

Embodiment(s)

An example of a system configuration of a substrate processing system according to an embodiment of the present invention will be described with reference to fig. 1. Fig. 1 is a block diagram showing an example of a system configuration of a substrate processing system according to the present embodiment.

As shown in fig. 1, a substrate processing system 1 in the present embodiment includes a substrate processing apparatus 10, a measuring apparatus 11, a parameter deriving apparatus 12, a shape simulator 13, and a process condition optimizing apparatus 14. The substrate processing apparatus 10, the measuring apparatus 11, the parameter deriving apparatus 12, the shape simulator 13, and the processing condition optimizing apparatus 14 are connected in a data communication manner via a communication network such as a LAN (Local Area Network: local area network) or the Internet.

The substrate processing apparatus 10 performs various substrate manufacturing processes (e.g., dry etching, deposition, etc.) by conveying a plurality of pre-process wafers (objects to be processed). In addition, a part of the plurality of pre-process wafers is transported to the measurement device 11.

In the substrate processing apparatus 10, when various substrate manufacturing processes are performed, a processed wafer is sent out from the substrate processing apparatus 10. At this time, in the substrate processing apparatus 10, processing conditions (process data acquired in the execution of various substrate manufacturing processes, recipe parameters used in executing various substrate manufacturing processes, and the like) are maintained. In addition, a part of the plurality of processed wafers is transported to the measuring device 11.

The measuring device 11 measures the shape of the wafer before processing when the wafer before processing is transported from the substrate processing device 10. The measuring device 11 measures the cross-sectional shape after cutting the wafer before processing in the cross-sectional direction at various positions. Thus, the measurement device 11 generates a pre-process cross-sectional image indicating the cross-sectional shape of the wafer before processing. The measuring device 11 may also measure the shape of the upper surface of the wafer before processing. Thereby, the measurement device 11 generates a pre-process upper surface image indicating the shape of the upper surface of the wafer before processing.

The measurement device 11 generates pre-process image data (hereinafter, also simply referred to as "pre-process data") obtained by measuring the shape of the wafer before processing after measuring the shape of the wafer before processing. The pre-processing image data includes a pre-processing cross-sectional image. In the case where the measurement device 11 measures the shape of the upper surface of the wafer before processing, the image data before processing includes an image of the upper surface before processing.

The measuring device 11 measures the shape of the processed wafer when the processed wafer is transported from the substrate processing device 10, and generates processed image data (hereinafter, also referred to simply as "processed data") indicating the shape of the processed wafer. The post-processing image data includes a post-processing cross-sectional image representing the cross-sectional shape of the post-processing wafer. The post-processing image data may include a post-processing upper surface image indicating the shape of the upper surface of the post-processing wafer.

The measuring device 11 includes a scanning electron microscope (SEM: scanning Electron Microscope), a transmission electron microscope (TEM: transmission Electron Microscope), an atomic force microscope (AFM: atomic Force Microscope), a focused ion beam scanning electron microscope (FIB SEM: focused Ion Beam Scanning Electron Microscope), and the like.

The pre-process image data and post-process image data generated by the measurement device 11, the process data and recipe parameters held by the substrate processing device 10, and the like are sent as collection data to the parameter deriving device 12. Thereby, the collected data is stored in the storage unit of the parameter deriving device 12.

The parameter deriving device 12 reads the collected data stored in the storage unit, and generates simulation data to be input to the shape simulator 13. The parameter deriving device 12 stores the generated analog data in the storage unit.

The simulation data is an example of a combination of data representing a shape of the substrate before processing and data representing a shape after processing, and includes a combination of the image data before processing and the image data after processing included in the plurality of collected data. The simulation data are classified and managed for each data set of processing conditions (process data, recipe parameters, physical quantities (Virtual Sensor/Metrology: virtual Sensor/metrology) calculated from these observations, etc.) that give the same effect in the change of the shape of the object to be processed before and after the processing.

In the present embodiment, a data set of processing conditions that achieve the same effect in the change of the shape of the object to be processed before and after the processing is referred to as "Proxel (processing unit)". Proxel is the smallest unit of data (Process Element) in the processing of an object to be processed, and is the same name as the smallest unit of image (Picture Element) called "Pixel", and the smallest unit of Volume (Volume Element) called "Volume". In fact, the "same effect" means that the shape of the object to be processed is not necessarily changed identically, and the shape of the object to be processed is changed to the same extent (within a predetermined range).

The parameter deriving device 12 reads a plurality of combinations of the pre-processing image data and the post-processing image data included in the simulation data of the specific Proxel among the simulation data classified for each Proxel. The parameter deriving device 12 inputs the plurality of pieces of pre-processing image data included in the plurality of combinations read to the shape simulator 13, and acquires a plurality of pieces of predicted image data (hereinafter, also simply referred to as "predicted data") from the shape simulator 13.

When the pre-processing image data includes a pre-processing cross-sectional shape, the predicted image data includes a predicted cross-sectional image for predicting a cross-sectional shape of the object after the processing is performed. When the pre-processing image data includes a pre-processing upper surface shape, the predicted image data includes a predicted upper surface image for predicting an upper surface shape of the object after the processing is performed. When the pre-processing image data includes three-dimensional structure information generated from the pre-processing cross-sectional shape and the upper surface shape, the predicted image data includes three-dimensional structure information for predicting three-dimensional structure information after the processing is performed on the object to be processed.

When the shape simulator 13 is operated, the parameter deriving device 12 repeatedly inputs a plurality of pieces of pre-processing image data to the shape simulator 13 while changing the values of the simulation parameters. At this time, the parameter deriving device 12 changes the values of the simulation parameters so that the plurality of predicted image data repeatedly output from the shape simulator 13 approaches the corresponding plurality of processed image data.

In this way, the parameter deriving device 12 can derive the optimal simulation parameter value that maximizes the proximity between the plurality of predicted image data and the corresponding plurality of processed image data. That is, the parameter deriving device 12 can derive the global optimal solution.

The shape simulator 13 operates by inputting the pre-processing image data and the values of the simulation parameters from the parameter deriving device 12, and outputs predicted image data.

The processing condition optimizing device 14 determines model data or a combination of a plurality of model data that obtains a result close to target state data indicating an end state of the object to be processed, by using model data that reproduces a change of the object to be processed, which is constructed as an effect of various process steps. The model data may be stored in the processing condition optimizing device 14 in advance, or may be stored in another device that can be read by the processing condition optimizing device 14 via a communication network.

The processing condition optimizing device 14 selects, as an optimal solution, model data that changes the input start state data to end state data having a large proximity to the target state data, or a combination of a plurality of model data. The processing condition optimizing device 14 may select the model data or a combination of the model data as the optimal solution based on a plurality of target values such as the processing time, the environmental load index, and a combination thereof. The process condition optimizing device 14 determines setting data (recipe parameters) included in the model data selected as the optimal solution as setting values (control setting values) of control means constituting the substrate processing apparatus 10.

The process condition optimizing device 14 may output the determined control setting value to the substrate processing apparatus 10 to control the process performed by the substrate processing apparatus 10. In this case, the substrate processing apparatus 10 performs the process based on the control set value input from the process condition optimizing apparatus 14.

The processing condition optimizing device 14 may display the determined control setting value on the display device. The process condition optimizing device 14 may display the determined control setting value on a display device of a user terminal used by a user of the substrate processing apparatus 10. In this case, the user of the substrate processing apparatus 10 sets the control setting value displayed on the display device to the substrate processing apparatus 10. The substrate processing apparatus 10 performs a process based on a control set value set by a user.

The system configuration of the substrate processing system 1 shown in fig. 1 is an example, and there are various system configuration examples depending on the application and purpose. The division of the devices such as the substrate processing device 10, the measuring device 11, the parameter deriving device 12, the shape simulator 13, and the process condition optimizing device 14 of fig. 1 is an example. For example, the parameter deriving device 12, the shape simulator 13, and the processing condition optimizing device 14 may be integrated with at least two of them, and the parameter deriving device 12, the shape simulator 13, and the processing condition optimizing device 14 may be divided into various configurations.

< Hardware Structure >

The hardware configuration of the substrate processing system 1 in the present embodiment will be described with reference to fig. 2. The parameter deriving device 12, the shape simulator 13, and the process condition optimizing device 14 in the present embodiment are realized by, for example, a computer. Fig. 2 is a block diagram showing an example of a hardware configuration of a computer in the present embodiment.

As shown in fig. 2, the computer 500 has a CPU (Central Processing Unit: central processing unit) 501, a ROM (Read Only Memory) 502, a RAM (Random Access Memory: random access Memory) 503, an HDD (HARD DISK DRIVE: hard disk drive) 504, an input device 505, a display device 506, a communication I/F (Interface) 507, and an external I/F508. The CPU501, ROM502, and RAM503 form a so-called computer. The hardware of the computer 500 are connected to each other via a bus 509. The input device 505 and the display device 506 may be connected to the external I/F508 for use.

The CPU501 is an arithmetic device for realizing control and functions of the entire computer 500 by reading a program and data from a storage device such as the ROM502 or the HDD504 to the RAM503 and executing processing.

The ROM502 is an example of a nonvolatile semiconductor memory (storage device) capable of holding programs and data even when the power supply is turned off. The ROM502 functions as a main storage device that stores various programs, data, and the like necessary for the CPU501 to execute the various programs installed in the HDD 504. Specifically, the ROM502 stores data such as a boot program such as BIOS (Basic Input/Output System) and EFI (Extensible FIRMWARE INTERFACE) executed at the time of starting the computer 500, OS (Operating System) settings, and network settings.

The RAM503 is an example of a volatile semiconductor memory (storage device) in which programs and data are erased when power is turned off. The RAM503 is, for example, DRAM (Dynamic Random Access Memory: dynamic random access memory), SRAM (Static Random Access Memory: static random access memory), or the like. The RAM503 provides a work area developed when various programs installed in the HDD504 are executed by the CPU 501.

The HDD504 is an example of a nonvolatile storage device that stores programs and data. Programs and data stored in the HDD504 include an OS that is basic software for controlling the entire computer 500 and applications that provide various functions on the OS. In addition, the computer 500 may use a storage device (for example, SSD: solid STATE DRIVE (Solid state drive)) using a flash memory as a storage medium instead of the HDD 504.

The input device 505 is a touch panel, operation keys and buttons, a keyboard and a mouse, a microphone for inputting sound data such as sound, and the like for a user to input various signals.

The display device 506 is configured by a display such as a liquid crystal or an organic EL (electroluminescence) that displays a screen, a speaker that outputs audio data such as sound, and the like.

The communication I/F507 is an interface for data communication with the computer 500, which is connected to a communication network.

The external I/F508 is an interface with external devices. The external device includes a driving device 511 and the like.

The driving device 511 is a device for setting the recording medium 512. The recording medium 512 herein includes a medium for optically, electrically, or magnetically recording information such as a CD-ROM, a floppy disk, an optical disk, or the like. The recording medium 512 may include a semiconductor memory or the like for electrically recording information, such as a ROM or a flash memory. Thus, the computer 500 can read and/or write the recording medium 512 via the external I/F508.

The various programs to be installed on the HDD504 are installed by, for example, providing the distributed recording medium 512 to a drive device 511 connected to the external I/F508, and reading the various programs recorded on the recording medium 512 by the drive device 511. Or various programs installed in the HDD504 may be installed by being downloaded from a network other than the communication network via the communication I/F507.

< Concrete example of data collection >

A specific example of the collected data stored in the parameter deriving means 12 will be described. Fig. 3 is a diagram showing an example of collected data in the present embodiment.

As shown in fig. 3, the collection data 300 includes, as items of information, "step", "task ID", "pre-process image data", "process data, recipe parameters, and the like", "Proxel", "post-process image data".

In the "step", a name indicating a substrate manufacturing process is stored. The example of fig. 3 shows a case where "dry etching" is stored as "step".

The "task ID" stores therein an identifier for identifying a task executed by the substrate processing apparatus 10. Fig. 3 illustrates an example in which "PJ001", "PJ002", "PJ003" are stored as "task ID" of the dry etching.

The "pre-processing image data" stores the file name of the pre-processing image data generated by the measurement device 11. The example of fig. 3 shows: in the case of task id= "PJ001", the measurement device 11 generates the pre-process image data of the file name= "shape data LD001" for one pre-process wafer in the lot (wafer group) of the task.

In addition, the example of fig. 3 shows: in the case of task id= "PJ002", the measurement device 11 generates the pre-process image data of the file name= "shape data LD002" for one pre-process wafer in the lot (wafer group) of the task. Further, the example of fig. 3 shows: in the case of task id= "PJ003", the measurement device 11 generates the pre-process image data of the file name= "shape data LD003" for one of the wafers before processing in the lot (wafer group) of the task.

In the "process data, recipe parameters, and the like", processing conditions (process data, recipe parameters, and the like) held when the processed wafer is conveyed in the substrate processing apparatus 10 are stored. In the example of fig. 3, the "process data set—recipe parameter set 001_1" and the like include process data such as the following:

Data outputted from the substrate processing apparatus 10 during processing such as Vpp (potential difference), vdc (direct current self-bias voltage), OES (emission intensity based on emission spectrum analysis), reflect (reflected wave power), top DCS current (detection value of doppler flow meter), etc,

Data measured during the process such as PLASMA DENSITY (plasma density), ion energy, ion flux, etc.

In addition, the "process data set—recipe parameter set 001_1" and the like may include values calculated from data outputted from these substrate processing apparatuses 10 and data observed during processing.

In addition, in the example of fig. 3, in the "process data set-recipe parameter set 001_1" and the like, recipe parameters such as the following are included:

data set as a set value in the substrate processing apparatus 10 such as Pressure (Pressure in the chamber), power (Power of high-frequency Power supply), gas (Gas flow rate), temperature (Temperature in the chamber or Temperature on the surface of the wafer), and the like,

Data set as target values in the substrate processing apparatus 10 such as CD (limit size), depth (taper angle), taper (taper angle), tilting (tilt angle), bowing (bow), and the like.

The "Proxel" is stored with a Proxel name indicating a data set in which the process data (included in the recipe data set), the recipe parameters (included in the recipe parameter set), and the like stored in the "process data, recipe parameters, and the like" are classified. The example of fig. 3 shows: process data, recipe parameters, and the like corresponding to task ids= "PJ001" to "PJ003" are classified as "proxel_a", and process data, recipe parameters, and the like corresponding to task ids= "PJ004" to "PJ006" are classified as "proxel_b".

Proxel is a data set that is classified according to process data, recipe parameters, etc. Therefore, as shown in fig. 3, even if different tasks are performed, the same Proxel is classified as long as the process data, the recipe parameters, and the like are the same.

The "processed image data" stores the file name of the processed image data generated by the measuring device 11. The example of fig. 3 shows: in the case of task id= "PJ001", the measurement device 11 generates processed image data of the file name= "shape data LD001'" for one processed wafer in the lot (wafer group) of the task.

In addition, the example of fig. 3 shows: in the case of task id= "PJ002", one processed wafer in the batch (wafer group) of the task is generated by the measurement device 11; the processed image data of file name= "shape data LD 002'". Further, the example of fig. 3 shows: in the case of task id= "PJ003", the measurement device 11 generates processed image data of the file name= "shape data LD003'" for one of the processed wafers in the lot (wafer group) of the task.

< Functional Structure of parameter deriving device >

Fig. 4 is a block diagram showing an example of the functional configuration of the parameter deriving device 12 according to the present embodiment. As shown in fig. 4, the parameter deriving device 12 of the present embodiment includes a parameter deriving unit 121, a collected data storing unit 122, and an analog data storing unit 123. The parameter derivation unit 121 includes a generation unit 410, an acquisition unit 420, a summary unit 430, a calculation unit 440, a derivation unit 450, and an output unit 460.

The parameter deriving unit 121 is realized by, for example, the CPU501 shown in fig. 2 executing a program loaded on the RAM 503. The collected data storage section 122 and the analog data storage section 123 are realized by, for example, a RAM503 or an HDD504 shown in fig. 2.

The generating unit 410 reads the collected data stored in the collected data storage unit 122, and generates simulation data. The generation unit 410 stores the generated analog data in the analog data storage unit 123. The generating unit 410 generates analog data for each same Proxel.

The acquisition unit 420 reads, from the analog data storage unit 123, a plurality of pieces of pre-processing image data among a plurality of combinations of pre-processing image data and post-processing image data included in the analog data of the specific Proxel. The acquisition unit 420 inputs the read plurality of pieces of pre-processing image data to the shape simulator 13, thereby operating the shape simulator 13.

When the shape simulator 13 is operated using simulation data of a specific Proxel, the summary unit 430 generates an item of simulation parameters to be input to the shape simulator 13. The summary unit 430 generates items of simulation parameters by referring to items of process data, items of recipe parameters, and the like constituting the Proxel.

The calculation unit 440 acquires a plurality of pieces of predicted image data output from the shape simulator 13 by inputting a plurality of pieces of pre-processing image data by the acquisition unit 420. The calculation unit 440 reads a plurality of pieces of processed image data corresponding to the plurality of pieces of pre-processed image data from the analog data storage unit 123, and calculates the proximity between each piece of processed image data and each piece of acquired predicted image data. The calculating unit 440 notifies the deriving unit 450 of each calculated proximity (proximity of the number corresponding to the number of processed image data and predicted image data).

For example, ioU (Intersection over Union: cross ratio) can be used as the proximity in the present embodiment. IoU the evaluation index is an index indicating the degree to which two areas overlap. IoU the evaluation index is a value obtained by dividing the common part of the two regions by the sum of the regions. IoU the evaluation index takes a value of 0 to 1, and the closer the value is to 1, the closer the evaluation is to 2 regions.

However, the proximity in the present embodiment is not limited to IoU evaluation indexes. For example, any evaluation index may be used as long as it is a method capable of evaluating the similarity of images such as the distance between feature amounts extracted from the images. Alternatively, the evaluation index may be used not only as the proximity but also as a combination of these indices such as the processing time and the environmental load index.

The deriving unit 450 calculates the value of the simulation parameter input to the shape simulator 13. The deriving unit 450 first sets predetermined initial values for the respective items of the simulation parameters generated by the summary unit 430, and inputs the initial values to the shape simulator 13.

Next, the deriving unit 450 obtains the proximity from the calculating unit 440. The deriving unit 450 changes the value of the simulation parameter so that each acquired proximity becomes larger. The deriving unit 450 inputs the changed values of the simulation parameters to the shape simulator 13. The deriving unit 450 repeats these processes until each of the proximity degrees is equal to or greater than a predetermined threshold (for example, 0.99).

The output unit 460 acquires the value of the simulation parameter when each of the proximity degrees calculated by the calculation unit 440 is equal to or greater than a predetermined threshold value from the derivation unit 450. The output unit 460 outputs the value of the simulation parameter acquired from the deriving unit 450 as the optimal value of the simulation parameter.

Specific example of processing of each section of parameter deriving device

A specific example of the processing of each unit (here, the generating unit 410, the summary unit 430, the calculating unit 440, and the deriving unit 450) of the parameter deriving device 12 will be described.

(1) Specific example of processing in the generating section

First, a specific example of the processing of the generating unit 410 will be described. Fig. 5 is a diagram showing a specific example of the processing of the generating unit.

As shown in fig. 5, the generation unit 410 reads the collected data 300 from the collected data storage unit 122, and generates analog data for each identical Proxel.

The example of fig. 5 shows the following scenario:

the generation unit 410 generates based on the collected data 300

Analog data 510 (data name= "analog data a")

Analog data 520 (data name= "analog data B")

Analog data 530 (data name= "analog data C").

In the example of fig. 5, the simulation data 510 is simulation data composed of a combination associated with Proxel name= "proxel_a" among a plurality of combinations included in the collected data 300.

Similarly, in the example of fig. 5, the simulation data 520 is simulation data composed of a combination associated with Proxel name= "proxel_b" among a plurality of combinations included in the collected data 300.

Similarly, in the example of fig. 5, the simulation data 530 is simulation data composed of a combination associated with Proxel name= "proxel_c" among a plurality of combinations included in the collected data 300.

As described above, the parameter deriving unit 121 derives the optimal value of the simulation parameter using the simulation data of the same Proxel. The example of fig. 5 shows:

deriving the optimal values of the simulation parameters using the simulation data 510, outputting the simulation parameter set a,

Deriving the optimal values of the simulation parameters using the simulation data 520, outputting the set of simulation parameters B,

Deriving the optimal values of the simulation parameters using the simulation data 530, outputting the simulation parameter set C.

Next, a specific example of the analog data will be described. Fig. 6 is a diagram showing a specific example of the analog data stored in the analog data storage unit 123.

In fig. 6, the pre-processing image data shown on the left side of the paper surface is the pre-processing image data whose file names are "shape data LD001", "shape data LD005", "shape data LD 006". On the other hand, in fig. 6, the processed image data shown on the right side of the paper surface is processed image data having file names of "shape data LD001'", "shape data LD005'", and "shape data LD006 '".

As described above, the common simulation parameter set a composed of the values of the optimal simulation parameters is output for a plurality of combinations of the pre-processing image data and the post-processing image data included in the simulation data 510. The generation unit 410 generates the simulation data 510 using image data having different shapes so that the simulation parameter set a outputted at this time becomes an optimal solution in a wider range.

Specifically, the analog data 510 is configured such that the shape of the pre-processing image data included in any one combination is different from the shape of the pre-processing image data included in any other combination (see left side of the drawing of fig. 6). The analog data 510 is configured such that the shape of the processed image data included in any one combination is different from the shape of the processed image data included in any other combination (see right side of the drawing of fig. 6). That is, the simulation data of each of the same proxels is composed of a combination in which the shape before or after the treatment is different from the shape before or after the treatment of the other combination.

As described above, the parameter deriving unit 121 derives the optimal simulation parameters not by using only a plurality of combinations but by using a plurality of combinations having different shapes. As a result, the parameter deriving unit 121 can derive an optimal solution over a wider range.

In addition, fig. 6 shows an example in which both the pre-processing image data and the post-processing image data have shapes different from each other. However, it is also possible that either of the pre-processing image data and the post-processing image data has a shape different from each other.

The simulation data in the present embodiment includes processed image data obtained by performing a process at a plurality of pattern densities for each of a plurality of mask shapes. Fig. 7 is a diagram showing an example of simulation data generated at a plurality of pattern densities for each of a plurality of mask shapes. As shown in fig. 7, the plurality of mask shapes include, for example, a line shape (trench shape) and a hole shape. In addition, various pattern densities represent the size (density) of the line (trench) or the space of the hole achieved by the process treatment. The pattern may include a lattice arrangement, a hexagonal packing arrangement, or the like.

The analog data in the present embodiment includes processed image data having different processing times for each process. Fig. 8 is a diagram showing an example of simulation data generated at a plurality of processing times. As shown in fig. 8, the plurality of processing times includes a predetermined processing time T1 and a processing time T2 longer than the processing time T1.

The simulation data may include processed image data obtained by performing a process at a plurality of processing times in a combination of a plurality of mask shapes and a plurality of pattern densities. The simulation data may also include processed image data obtained by performing a process at a plurality of processing times in all combinations of a plurality of mask shapes and a plurality of pattern densities.

The processing time intervals can be shortened in the vicinity of the boundary between layers of different film types in the object to be processed. For example, when the post-processing image data is generated at intervals of Δt1 in the L-th layer, the post-processing image data may be generated at intervals of Δt2 shorter than Δt1 when the processing proceeds from the L-th layer to the l+1th layer. For example, in the dry etching process, the process speed per unit time is the same in the same film type, but the process speed per unit time is different between different film types. Therefore, when the processed image data is generated at shorter time intervals in the vicinity of the boundary where the film types are switched, it is expected that the simulation parameters capable of reproducing the change of the object to be processed with higher accuracy can be obtained.

(2) Specific example of processing of summary

Next, a specific example of the processing of the summarizing section 430 will be described. Fig. 9 is a diagram showing a specific example of the process of the headquarter.

As shown in fig. 9, the aggregation unit 430 includes a Proxel acquisition unit 701, a simulation parameter item generation unit 702, and a simulation parameter item output unit 703.

The Proxel acquiring unit 701 acquires items of process data and items of recipe parameters of Proxel configured to correspond to specific simulation data among the simulation data stored in the simulation data storage unit 123.

Proxel_a to proxel_c, which are examples of Proxel, are generated by dividing a multidimensional space 700 composed of items of process data, items of recipe parameters, and the like into small spaces with grid lines (plot) having the same effect. Space 700 shown in fig. 9 shows a small space of each Proxel generated by dividing a three-dimensional space constituted by the power of the high-frequency power source, the power of the low-frequency power source, and the pressure in the chamber.

In the Proxel acquisition unit 701, when the optimum value of the simulation parameter is derived using the simulation data of proxel_a, the values constituting proxel_a are acquired,

Items and values of process data (contained in process data set 001),

Items and values of scheme parameters (contained in scheme parameter set 001), and the like.

Fig. 9 shows an example in which the Proxel acquiring unit 701 acquires the power of the high-frequency power supply, the power of the low-frequency power supply, and the pressure in the chamber.

The simulation parameter item generating unit 702 generates an item a of the simulation parameter of the shape simulator 13 by referring to the item and value of the process data and the item and value of the recipe parameter acquired by the Proxel acquiring unit 701. The simulation parameter item generating unit 702 generates an item a by classifying, for example, simulation parameters of a particle type and simulation parameters of a reaction type. Further, when the simulation parameter item generating unit 702 generates an item of a simulation parameter, domain knowledge may be reflected.

Fig. 9 shows an example of items of simulation parameters of the particle type, the amount of the isotropic etching component generated, and the like. In addition, items are shown as simulation parameters of the reaction species, and amounts related to ion behaviors, ion angular distributions, angular distributions of sputtering efficiency, and the like are generated.

As described above, the simulation parameter item generating unit 702 abstracts items of process data, items of recipe parameters, and the like constituting Proxel into categories of reaction elements that do not overlap as physical phenomena, thereby generating the item a of simulation parameters. Thus, the simulation parameter item generating unit 702 can generate the item a with the dimension reduced simulation parameters.

The simulation parameter item output unit 703 outputs the item a of the simulation parameter generated by the simulation parameter item generation unit 702 to the derivation unit 450.

Fig. 10 is a diagram showing a specific example of recipe parameters in the dry etching process. Fig. 11 is a diagram showing a specific example of simulation parameters of the shape simulator 13 generated based on the recipe parameters shown in fig. 10. The initial values (P11 to P18) to be set as the simulation parameters may be values actually measured by the sensors in the process, values disclosed in the literature, or the like, values optimized in the similar process, or random values, or the like.

(3) Specific example of processing by the computing section

Next, a specific example of the processing of the calculating unit 440 will be described. Fig. 12 is a diagram showing a specific example of the processing of the calculating unit.

As shown in fig. 12, the calculation section 440 includes a post-processing image data acquisition section 901, a predicted image data acquisition section 902, and a proximity calculation section 903.

The post-processing image data acquisition section 901 acquires post-processing image data (e.g., shape data LD001', LD005', LD006 ') corresponding to a plurality of pre-processing image data (e.g., shape data LD001, LD005, LD 006) input to the shape simulator 13. The post-processing image data acquisition unit 901 also notifies the proximity calculation unit 903 of the acquired post-processing image data.

The predicted image data acquiring unit 902 acquires a plurality of predicted image data (for example, shape data LD101', LD105', LD106 ') based on the fact that a plurality of pre-processing image data (for example, shape data LD001, LD005, LD 006) are input to the shape simulator 13. The predicted image data acquiring section 902 also notifies the acquired predicted image data to the proximity calculating section 903.

The proximity calculation section 903 calculates the proximity of the processed image data (e.g., the shape data LD001', LD005', LD006 ') notified by the processed image data acquisition section 901 and the predicted image data (e.g., the shape data LD101', LD105', LD 106') notified by the predicted image data acquisition section 902, respectively. The proximity calculation unit 903 notifies the derivation unit 450 of the calculated proximity. The proximity calculation unit 903 calculates the number of proximity degrees corresponding to the number of pieces of pre-processing image data input to the shape simulator 13, and notifies the derivation unit 450 of each calculated proximity degree.

(4) Specific example of processing in the deriving section

Next, a specific example of the processing of the deriving unit 450 will be described. Fig. 13 is a diagram showing a specific example of the processing of the deriving unit.

As shown in fig. 13, the deriving unit 450 includes an analog parameter item acquiring unit 801, an initial value setting unit 802, an analog parameter input unit 803, a value changing unit 804, and a proximity acquiring unit 805.

The simulation parameter item acquisition unit 801 acquires an item of a simulation parameter (for example, "item a of a simulation parameter") from the summary unit 430, and sets the item to the simulation parameter input unit 803.

The initial value setting unit 802 sets initial values corresponding to the respective items of the simulation parameters in the simulation parameter input unit 803.

When a plurality of pieces of pre-processing image data are input to the shape simulator 13, the simulation parameter input unit 803 inputs values of simulation parameters. The analog parameter input unit 803 first inputs an initial value, and then inputs a value instructed to be changed by the value change unit 804.

The analog parameter input unit 803 outputs an analog parameter set (herein, "analog parameter set a") composed of values of optimal analog parameters whose respective degrees of proximity are equal to or greater than a predetermined threshold value to the output unit 460.

The value changing unit 804 instructs the analog parameter input unit 803 to change the value of the analog parameter. Specifically, each time each proximity is notified from the proximity acquisition unit 805, the value change unit 804 instructs the analog parameter input unit 803 to change the value according to each notified proximity. In addition, the value changing unit 804 instructs the simulation parameter input unit 803 to change the number of items of the simulation parameter in accordance with the number of items of the simulation parameter. The change instruction by the value changing unit 804 includes a change direction (increase/decrease) and a change amount.

Thus, the simulation parameter input unit 803 can input the values of the simulation parameters corresponding to the respective degrees of proximity of the plurality of processed image data and the plurality of predicted image data to the shape simulator 13.

The proximity acquisition unit 805 acquires each proximity notified from the calculation unit 440. The proximity acquisition section 805 acquires the respective proximity of the number corresponding to the number of the pre-processing image data input to the shape simulator 13.

The proximity acquisition unit 805 compares each acquired proximity with each previously acquired proximity to determine whether each proximity has been enlarged or reduced. The proximity acquisition unit 805 also notifies the value change unit 804 of each calculated proximity and the determination result. In this way, the value changing unit 804 can determine a change instruction (including a change direction and a change amount) of the value of each simulation parameter.

< Processing step of parameter derivation method >

Fig. 14 is a flowchart showing an example of the parameter derivation method according to the present embodiment. The parameter derivation method in the present embodiment is executed by the parameter derivation device 12.

In step S1, the generation unit 410 reads the collected data stored in the collected data storage unit 122. The generating section 410 generates analog data based on the read collected data. The generation unit 410 stores the generated analog data in the analog data storage unit 123.

In step S2, the acquisition section 420 reads a plurality of pieces of pre-processing image data from the analog data stored in the analog data storage section 123. The acquisition unit 420 inputs the read plurality of pieces of pre-processing image data to the shape simulator 13.

In step S3, the summarizing unit 430 generates an item of simulation parameters input to the shape simulator 13. The summary section 430 sends the generated items of the simulation parameters to the derivation section 450.

In step S4, the deriving unit 450 receives the items of the simulation parameters from the summarizing unit 430. When step S4 is performed for the first time, the deriving unit 450 sets a predetermined initial value for each item of the simulation parameter, and inputs the value of the simulation parameter for which the initial value is set to the shape simulator 13. When step S4 is performed a second time and thereafter, the deriving unit 450 inputs the value of the simulation parameter changed in step S8 to the shape simulator 13.

The shape simulator 13 operates using the plurality of pieces of pre-processing image data input from the acquisition unit 420 and the values of the simulation parameters input from the derivation unit 450, and outputs a plurality of pieces of predicted image data. The plurality of predicted image data outputted from the shape simulator 13 are sent to the calculation section 440.

In step S5, the calculation unit 440 acquires a plurality of pieces of predicted image data output from the shape simulator 13. The calculation section 440 reads a plurality of pieces of processed image data corresponding to a plurality of pieces of predicted image data from the analog data stored in the analog data storage section 123.

In step S6, the calculating unit 440 calculates the proximity between the acquired plurality of predicted image data and the plurality of processed image data, respectively. The calculation unit 440 transmits each calculated proximity to the derivation unit 450.

In step S7, the deriving unit 450 receives the plurality of proximity degrees from the calculating unit 440. The deriving unit 450 determines whether or not each received proximity is equal to or greater than a predetermined threshold. When the respective approaches are equal to or greater than the threshold value (YES), the deriving unit 450 sends the value of the simulation parameter to the output unit 460, and the process proceeds to step S9. On the other hand, when the respective approaches are smaller than the threshold value (NO), the deriving unit 450 advances the process to step S8.

The deriving unit 450 may determine that each proximity is equal to or greater than the threshold value when all the proximity is equal to or greater than the threshold value. The deriving unit 450 may determine that each proximity is equal to or greater than the threshold value when the ratio of the proximity equal to or greater than the threshold value is equal to or greater than a predetermined value. The deriving unit 450 may determine that each proximity is equal to or greater than a threshold value when a statistical value (for example, an arithmetic average, a central value, or the like) of each proximity is equal to or greater than the threshold value.

In step S8, the deriving unit 450 changes the value of the simulation parameter so that the respective proximity degrees received from the calculating unit 440 become larger. After that, the deriving unit 450 returns the process to step S4. In this way, the processing in steps S4 to S7 is repeatedly performed until the respective proximity degrees calculated by the calculation unit 440 become equal to or greater than the predetermined threshold value.

In step S9, the output unit 460 receives the value of the simulation parameter from the deriving unit 450. The output unit 460 outputs the received value of the simulation parameter as the optimal value of the simulation parameter.

The value of the simulation parameter outputted from the output unit 460 is transmitted to the processing condition optimizing device 14, for example. Thus, the simulation parameters optimized are stored in the storage unit of the process condition optimizing device 14.

< Functional Structure of treatment condition optimizing apparatus >

Fig. 15 is a block diagram showing an example of the functional configuration of the processing condition optimizing device 14 according to the present embodiment. As shown in fig. 15, the processing condition optimizing apparatus 14 according to the present embodiment includes a model storage section 140, a data input section 141, a modulation section 142, a prediction section 143, a determination section 144, and a setting value output section 145.

The data input unit 141, the modulation unit 142, the prediction unit 143, the determination unit 144, and the setting value output unit 145 can be realized by, for example, the CPU501 shown in fig. 2 executing a program loaded on the RAM 503. The model storage unit 140 can be implemented by, for example, the RAM503 or the HDD504 shown in fig. 2.

The model storage unit 140 stores model data that reproduces changes in the object to be processed, which is constructed as an effect of various processing. The model data includes recipe parameters for the process and simulation parameters set based on the recipe parameters. Model data is generated for each process performed by the substrate processing apparatus 10.

Fig. 16 is a diagram showing a specific example of model data in the present embodiment. As shown in fig. 16, the model data is associated with each process, and identification information for identifying the model data, recipe parameters of the process, and simulation parameters optimized for the process are associated with each other.

The simulation parameters are simulation parameters of the shape simulator 13 derived by the parameter derivation means 12. Therefore, the simulation parameters included in the model data are set with values of the simulation parameters that cause the shape simulator 13 to operate so as to reproduce the experimental results with high accuracy.

The data input unit 141 accepts input of start state data and target state data by a user. For example, the data input unit 141 accepts input of start state data and target state data according to an operation of the input device 505 by a user. For example, the data input unit 141 may receive input of the start state data and the target state data by receiving the start state data and the target state data from a user terminal such as a personal computer operated by a user.

The start state data is, for example, data including three-dimensional structural information and texture information of the object to be processed before processing, which is modeled by the shape modeling software. The start state data may be data including two-dimensional structure information and texture information of the object to be processed before the processing. The start state data may be data including one-dimensional structure information and texture information as long as the start state data can indicate structure information and texture information of the object to be processed before the process.

In the case where the process treatment includes a dry etching treatment, the start state data contains, for example, structural information and material information of the etching mask and the etching film. The dry process may be a film forming process such as chemical vapor deposition, or chemical vapor deposition. In the case where the process includes a film formation process, the start state data includes, for example, structural information and material information of a base layer to be formed and a film to be formed.

The target state data is, for example, data including three-dimensional structural information and texture information of the object to be processed, which is a target after the process, obtained by modeling by the shape modeling software. The target state data may be data including two-dimensional structural information and texture information of the object to be processed, which is the target after the process. The target state data may be data including one-dimensional structure information and texture information as long as the structure information and texture information of the object to be processed as a target after the process are expressed.

The modulation unit 142 generates one or more pieces of modulation data by changing the start state data input to the data input unit 141. The modulation data is data for changing a part of the structure or material of the object to be processed in the start state data. The modulated data may also contain the start state data itself.

Fig. 17 and 18 are conceptual diagrams illustrating an example of modulated data in the present embodiment. As shown in fig. 17, the modulation data is generated by changing predetermined items in an image (a cross-sectional image and/or an upper surface image) representing the structure or material of the object to be processed shown in the start state data. Regarding the modulation data, at least one item such as film type, film thickness, pattern width, inclination shape, chamfer shape, taper shape, or surface roughness is changed. The modulation data may be, for example, two or more of a film type, a film thickness, a pattern width, an inclined shape, a chamfer shape, a tapered shape, and a surface roughness.

Parameters for change are set in each item. For example, when the film type is changed, the layer number, the material before the change, and the material after the change are parameters. Similarly, when the film thickness is changed, the layer number, the thickness before the change, and the thickness after the change become parameters. When the chamfer shape is changed, the roundness coefficient after the change becomes a parameter. When the surface roughness is changed, the amount of noise (for example, period, amplitude, etc.) after the change becomes a parameter. When the pattern width is changed, the changed width becomes a parameter. When the taper shape and the inverted taper shape are changed, the changed taper angle becomes a parameter. When the inclination shape is changed, the changed inclination angle becomes a parameter.

The amount of change of each parameter may be determined by a predetermined option, may be specified from a predetermined range, or may be determined randomly. For example, when the film thickness is changed, the change amount may be selected from the options of 10nm, 20nm, or 30nm, or may be determined from the range of 10nm to 30 nm.

As shown in fig. 18, the modulation data may include a plurality of modulation data obtained by changing one item with different parameters. For example, when the proximity of the tapered shape is estimated to be higher than the proximity of the chamfer shape, the probability that the optimal solution approaches the tapered shape is high. In this case, only a plurality of modulation data (for example, 3 modulation data having a large, medium, and small taper angle) having a different taper shape among different taper angles (for example, 3 of large, medium, and small taper angles) may be generated.

The modulation unit 142 may generate modulation data when model data satisfying a predetermined criterion cannot be obtained for the start state data input to the data input unit 141. The predetermined criterion is, for example, that the proximity of the end state data predicted by the prediction unit 143 to the target state data is equal to or greater than a predetermined threshold (for example, 0.99).

The prediction unit 143 predicts the end state data of the object to be processed by simulating the process-based change in the modulation data generated by the modulation unit 142 using the model data or the combination of the plurality of model data stored in the model storage unit 140.

The determination unit 144 determines end state data and modulation data close to the target state data from the end state data of the object predicted by the prediction unit 143. When the specified modulation data is the start state data itself, the determination unit 144 selects, as an optimal solution, model data that changes the inputted modulation data to end state data having a large proximity to the target state data, or a combination of a plurality of model data. The determination unit 144 determines the recipe parameters included in the model data selected as the optimal solution as control setting values to be output to the substrate processing apparatus 10. When the determined modulation data is not the start state data itself, the determination unit 144 notifies the user of the need to modulate to the start state data in order to obtain the optimal solution.

The set value output unit 145 outputs the control set value determined by the determination unit 144 to the substrate processing apparatus 10. The output of the setting value output unit 145 may include information indicating the optimal solution of the model data or the combination of the plurality of model data determined by the determination unit 144.

< Functional Structure of substrate processing apparatus >

Referring back to fig. 15, an example of the functional configuration of the substrate processing apparatus 10 according to the present embodiment will be described. As shown in fig. 15, the substrate processing apparatus 10 of the present embodiment includes a set value input section 101, a condition input section 102, and a process control section 103.

The set value input unit 101 receives input of a control set value from the process condition optimizing device 14.

The condition input unit 102 inputs the control setting value input from the process condition optimizing device 14 as a process condition to the process control unit 103. Thereby, the condition input section 102 controls the operation of the process control section 103.

The process control unit 103 performs a process based on the inputted control setting value.

< Example of method for optimizing treatment Condition >

Fig. 19 is a flowchart showing an example of the process condition optimization method according to the present embodiment. The processing condition optimizing method in the present embodiment is executed by the processing condition optimizing device 14.

In step S11, the data input unit 141 accepts input of start state data and target state data. Next, the data input section 141 transmits the start state data to the modulation section 142. The data input unit 141 sends the target state data to the determination unit 144.

In step S12, the modulation unit 142 receives start state data from the data input unit 141. Next, the modulation unit 142 generates one or more modulated data by changing one or more parameters of the start state data. The modulated data may also contain the start state data itself. Next, the modulation unit 142 stores the generated one or more modulation data in a storage unit such as the HDD 504.

In step S13, the prediction unit 143 reads one of the modulated data stored in the storage unit. The modulated data may be read cyclically, randomly by a predetermined number of times, or up to an allowable proximity.

In step S14, the prediction unit 143 reads the model data or the combination of the plurality of model data stored in the model storage unit 140. The reading of the model data or the combination of the plurality of model data may be performed cyclically, or may be performed randomly by determining the number of times, or may be performed until an allowable proximity is reached.

Fig. 20 and 21 are conceptual diagrams illustrating an example of a process of reading a combination of a plurality of model data. In fig. 20 and 21, the model data is described as "Proxel". Fig. 20 is an example of a combination of 5 model data. Fig. 21 is an example of a combination of 6 model data. As shown in fig. 20 and 21, a plurality of pieces of identical model data may be included in a combination of a plurality of pieces of model data.

The process of reading a combination of a plurality of model data may be performed as shown in fig. 22. Fig. 22 is a conceptual diagram showing an example of a process of reading a combination of a plurality of model data. Fig. 22 is an example of a combination of three model data, showing an example in which the first model data "ProxelA" and the third model data "ProxelC" are directly specified by the user. In the example of fig. 22, different combinations of a plurality of model data are read by inserting and switching the second model data.

The description returns to fig. 19. In step S15, the prediction unit 143 predicts the end state data of the object to be processed by simulating a change in the object to be processed due to the process, which is represented by the modulated data read in step S13, using the model data read in step S14 or a combination of a plurality of model data.

Fig. 23 is a conceptual diagram illustrating an example of the prediction process. For example, in the case where one piece of model data is read in step S14, as shown in fig. 23, one piece of model data is used to predict the end state data from the modulation data. The model data is associated with the effect of the predetermined process, and thus the end state data 1311 when the modulation data 1301 is input can be predicted. Similarly, the end state data 1312 can be predicted even when the modulated data 1302 is input. In this way, when the shape of the modulated data and the like are different, the model data of the present embodiment can predict different end state data corresponding to the modulated data.

In the case where a combination of a plurality of model data is read in step S14, a plurality of model data are used sequentially from the beginning to predict end state data from start state data. At this time, the start state data of the first model data becomes the modulated data, and the start state data of the second and subsequent model data becomes the end state data of the model data of the preceding order. In this way, the prediction unit 143 predicts the end state data of the object to be processed using the model data read from the model storage unit 140 in step S14, or the combination of a plurality of model data.

The description returns to fig. 19. In step S16, the determination unit 144 calculates the proximity (or the degree of deviation) between the end state data of the object predicted in step S15 and the target state data received in step S11.

In step S17, the determination unit 144 determines whether or not the reading of all the combinations of the model data and the plurality of model data is completed. When the reading of all the combinations of the model data and the plurality of model data is completed (yes), the determination unit 144 advances the process to step S18.

On the other hand, when the reading of all the combinations of the model data and the plurality of model data is not completed (no), the determination unit 144 returns the process to step S14. In this way, the processing in steps S14 to S17 is repeated until the calculation of the proximity using the combination of all the model data and the plurality of model data is performed with respect to any one of the modulation data.

In addition, the processing in steps S14 to S17 is repeated, and when the number of times of reading of the combination of the plurality of model data is determined and the combination is randomly performed, the process is performed until the number of times is reached. In addition, when the allowable proximity is reached, the calculation is performed until the allowable proximity is calculated.

In step S18, the determination unit 144 determines whether or not the reading of all the modulated data is completed. When the reading of all the modulated data is completed (yes), the determination unit 144 advances the process to step S19.

On the other hand, when all the modulated data are not read (no), the determination unit 144 returns the process to step S13. In this way, the processing in steps S13 to S18 is repeated until the calculation of the proximity using the combination of all the model data and the plurality of model data is performed on all the modulated data.

In step S19, the setting value output unit 145 selects, as an optimal solution, the model data having the greatest proximity (or the smallest deviation) calculated in step S16 or a combination of a plurality of model data. The set value output unit 145 may select the model data or the combination of model data having the greatest proximity calculated in step S16 when the modulation data is the start state data itself, and select the model data or the combination of model data having the greatest proximity calculated in step S16 as the optimal solution when the modulation data is not the start state data itself. The set value output section 145 outputs the selected optimum model data or the combination of the plurality of model data to the substrate processing apparatus 10.

In the substrate processing apparatus 10, a set value input section 101 receives an input of a control set value from a process condition optimizing apparatus 14. The condition input unit 102 inputs the control set value received by the set value input unit 101 as a process condition to the process control unit 103. The process control unit 103 performs a process based on the inputted control setting value.

In the processing condition optimizing method shown in fig. 19, when the number of model data stored in the model storage unit 140 increases, the number of combinations of the model data and the plurality of model data read in step S14 increases, and the time until the optimal solution is selected increases. Therefore, the process of reading the model data or the combination of the plurality of model data in step S14 may also achieve the high efficiency of the search for the optimal solution by performing machine learning using the proximity calculated in step S16 as the evaluation value.

Tree search, graph search, meta heuristic search, or a combination thereof may be used in the search of the optimal solution. Furthermore, reinforcement learning may be used in searching for the optimal solution to learn a selection pointer (Policy) for a process for obtaining end state data close to the target state data.

For example, a method of finding an optimal solution using a genetic algorithm based on the proximity calculated in step S16 may also be used. For example, a method of searching (reinforcement learning) using the degree of deviation from the target state data as a reward criterion, a method of learning the correlation between the degree of proximity to the target state data and the processing conditions of the processing, and searching (reinforcement learning) using the degree of deviation from the target state data as a reward criterion may be used.

Fig. 24 and 25 are conceptual diagrams illustrating an example of the processing performed by the processing condition optimizing apparatus 14 according to the present embodiment. Fig. 24 shows a process of searching for model data (Proxel) that obtains end state data close to target state data using the input start state data. On the other hand, fig. 25 shows a process of searching for model data (Proxel) that obtains end state data close to target state data using modulated data in which the shape (here, film thickness) of input start state data is changed.

< Effects of embodiments >

The parameter deriving device 12 in the present embodiment generates simulation data including a plurality of combinations of pre-processing data and post-processing data of the object to be processed, and derives simulation parameters of the shape simulator based on the proximity of prediction data predicted by inputting the pre-processing data included in the simulation data to the shape simulator and the post-processing data combined with the pre-processing data. The simulation data includes a combination of pre-process data and post-process data when the process is performed at a plurality of pattern densities for each of the plurality of mask shapes. The parameter deriving device 12 according to the present embodiment can derive the simulation parameters that can accurately predict the state of the object after the process is performed on the object.

The parameter deriving device 12 according to the present embodiment includes a plurality of pieces of processed data obtained by performing a process on a subject at different processing times. The parameter deriving device 12 according to the present embodiment can derive the simulation parameters that can predict the state of the object after the process has been performed on the object with higher accuracy.

In the parameter deriving device 12 of the present embodiment, the process may include etching of the substrate, and the pre-process data may include information on the structure of the etching mask and the etching film. In the parameter deriving device 12 of the present embodiment, the mask shape may include a line shape and a hole shape, and the pattern density may be a size of a line or a hole interval by a process. The parameter deriving device 12 according to the present embodiment can derive a simulation parameter capable of predicting the state of the object after the etching process is performed on the object with high accuracy.

The processing condition optimizing device 14 in the present embodiment stores simulation parameters of a shape simulator for reproducing a change in the object to be processed when the process is performed on the object to be processed under predetermined processing conditions, and generates modulation data in which the input start state data of the object to be processed is changed, and determines the processing condition of the process to be performed on the object to be processed based on the proximity of the end state data predicted by inputting the modulation data and the simulation parameters to the shape simulator and the input target state data. The processing condition optimizing device 14 according to the present embodiment can accurately predict the state of the object after the process is performed on the object, and as a result, can determine the processing condition capable of accurately reproducing the state of the object.

With regard to the process condition optimizing apparatus 14 in the present embodiment, the process treatment includes an etching process for the substrate, and the start state data may include structural information and material information of the etching mask and the etching film. In the processing condition optimizing apparatus 14 of the present embodiment, at least one of the film type, film thickness, pattern width, inclined shape, chamfer shape, tapered shape, and surface roughness can be changed. The processing condition optimizing device 14 of the present embodiment can determine the processing condition of the etching process capable of accurately reproducing the state of the target object to be processed.

[ Supplement ]

The parameter deriving device and the processing condition optimizing device of the presently disclosed embodiment are illustrative in all respects and not restrictive. The parameter deriving device and the processing condition optimizing device according to the above embodiment are examples of the information processing device. The embodiments can be modified and improved in various ways without departing from the scope of the appended claims and the gist thereof. The contents described in the above embodiments can be combined in a range not inconsistent with other structures.

Claims (12)

1. An information processing apparatus, characterized by comprising:

A generation unit configured to be capable of generating simulation data including a plurality of combinations of pre-processing data of a subject and post-processing data of the subject after performing a process treatment under predetermined treatment conditions, the combinations including the pre-processing data and the post-processing data when the process treatment is performed at a plurality of pattern densities for each of a plurality of mask shapes; and

And a deriving unit configured to derive simulation parameters of the shape simulator based on a proximity between prediction data predicted by inputting the pre-processing data included in the simulation data to the shape simulator and the post-processing data combined with the pre-processing data.

2. The information processing apparatus according to claim 1, wherein:

the processed data includes a plurality of the processed data after the processing is performed on the object to be processed at different processing times.

3. The information processing apparatus according to claim 2, wherein:

the process includes an etching process of the substrate,

The pre-process data includes structural information of the etching mask and the etching film.

4. The information processing apparatus according to claim 2, wherein:

the process treatment includes a film forming treatment for a substrate,

The pre-treatment data includes structural information of a base layer to be formed and a film to be formed.

5. The information processing apparatus according to claim 3 or 4, wherein:

The mask shape includes a line shape and an aperture shape,

The pattern density represents the size of the line or hole spacing achieved by the process treatment.

6. An information processing apparatus according to claim 3, wherein:

the generation unit is configured to generate a plurality of pieces of processed data having short processing time intervals in the vicinity of the boundary of the etching film.

7. An information processing apparatus, characterized by comprising:

A storage unit configured to be able to store simulation parameters of a shape simulator for reproducing a change in a target object when a process is performed on the target object under predetermined processing conditions;

An input unit configured to be able to receive input of start state data of the object to be processed and target state data of the object to be processed;

A modulating unit configured to generate modulated data in which the start state data is changed;

A prediction unit configured to be able to predict end state data after the processing is performed on the object under the processing conditions by inputting the modulation data and the simulation parameters to the shape simulator; and

And a determining unit configured to determine the processing condition of the process to be performed on the object to be processed based on a proximity of the end state data and the target state data.

8. The information processing apparatus according to claim 7, wherein:

the process includes an etching process of the substrate,

The start state data includes structural information of the etching mask and the etching film.

9. The information processing apparatus according to claim 8, wherein:

the start state data further includes material information of the etching film.

10. The information processing apparatus according to claim 7, wherein:

the process treatment includes a film forming treatment for a substrate,

The start state data includes structural information of a base layer to be formed and a film to be formed.

11. The information processing apparatus according to claim 9, wherein:

the modulation unit is configured to be capable of changing at least one of a film type, a film thickness, a pattern width, an inclined shape, a chamfer shape, a tapered shape, and a surface roughness.

12. An information processing method, characterized by comprising:

a step of generating simulation data including a plurality of combinations of pre-processing data of a subject and post-processing data of the subject after performing a process treatment under predetermined treatment conditions, the combinations including the pre-processing data and the post-processing data when the process treatment is performed at a plurality of pattern densities for each of a plurality of mask shapes; and

Deriving simulation parameters of the shape simulator based on the proximity of prediction data predicted by inputting the pre-processing data included in the simulation data to the shape simulator and the post-processing data combined with the pre-processing data.